Building agents skills

huangxinxinyu/xinyu-s-skill-set

Skill Claude CodeCodex

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

xiaoshiyilangzhao1996-droid/yinyo-agent-harness

Skill Claude CodeCodex

An evaluation and audit workflow based on the HARNESS.md v1.0 specification. It checks whether the current workspace follows that specification and guides improvements supported by evidence.

jackielszhang/human-model

Skill Codex

Protects the parts of a user's thinking they want to keep human. Use for product direction, original interaction ideas, taste, judgement, synthesis, human feel, exploration, personal philosophy, first-run boundary setup, Human Model corrections, or /human-model commands. Do not interfere with routine execution…

achaykovsky/Cursor-Usage-Templates

Skill Claude CodeCodex

Performs LLM system design review (not code review) across hallucination risks, context explosion, retrieval quality, prompt coupling, observability, evaluation, confidence calculation, deterministic business logic, tenant isolation, future tool calling, cost, and latency. Use for bot/RAG architecture review…

MatthewYe/opencode-toolbox

Skill Claude CodeCodex

Create, modify, and improve agent skills with iterative eval-driven development. Use when user wants to create a new skill from scratch, edit or optimize an existing skill, run evals to test skill performance, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering…

deomiarn/claude-setup-template

Skill Claude Code

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords…

oager/claude-wiki-engine

Skill Claude CodeCodex

Three-model build pipeline routing design, spec/verification, and implementation to cost-appropriate models with hard gates (Fable design, Opus spec+verify, Sonnet build). Trigger on 'tiered build', 'run my pipeline', 'design-then-build', /tiered-build, or handing over a design doc to take to the next phase.

dungnotnull/black-soldier-fly-waste-processing-agent-skill

Skill Claude CodeCodex

Skill "black-soldier-fly-waste-processing-agent-skill" from dungnotnull/black-soldier-fly-waste-processing-agent-skill, covering skill.md - skill registry documentation, 1. registry overview, 2. registered skills, 3. how skills are registered and 4. how skills are resolved.

lehuutrung1412/dotfiles

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

casualsav/fable-bench

Skill Claude CodeCodex

Have Claude Fable 5 plan the current task, then run an automatic warm diff-review after you execute. You (the below-Fable driver — Sonnet or Opus) gather the evidence and execute; Fable is the context-blind PLANNER — one plan engagement at the start (it writes the plan, unanchored by any draft of yours), one warm…

ahmedkhaledmohamed/PM-AI-Partner-Framework

Skill Claude Code

Hands-on implementation partner for creating tools, scripts, dashboards, and prototypes. Use when the user wants to build something tangible — apps, scripts, automations, or internal tools. Triggers include "build", "create tool", "make app", "implement", "prototype", "automate", or when the goal is working software.

armenr/ctx-fieldbook

Skill Claude Code

Capture current session state to a curated artifact at .agent-docs/now/handoff.md plus an archive entry at .claude/handoffs/ - .md. Updates now/status.md, now/work-plan.md, now/open-questions.md, log.md to current reality; sweeps the inter-party obligations ledger both directions (owed-by / owed-to, each receivable…

dungnotnull/craft-village-heritage-tourism-agent-skill

Skill Claude CodeCodex

The SKILL Registry is the central system for managing, resolving, and executing all skills in the craft-village-heritage-tourism project — a Claude Code harness for the Craft-Village Heritage Tourism & Living Culture domain. This document describes how skills are registered, how they are resolved during execution…

walidboulanouar/agent-aware

Skill Claude CodeCodex

How an agent should reason about what it has, what it can do, what to delegate, and how to verify without assumptions. Read before starting any non-trivial autonomous task. Covers self-inventory, verification levels, assumption audit, and when to stop and escalate.

dungnotnull/aim-training-sensitivity-converter-agent-skill

Skill Claude CodeCodex

Skill Registry System for Aim Training & Sensitivity Converter - Comprehensive documentation of skill registration, resolution, execution, and validation protocols. Use this when managing skill lifecycle, understanding skill architecture, or implementing new skills in the system.

Volchunovich/gum

Skill Claude Code

Create a new GUM module with rules and optional hooks.

dungnotnull/team-synergy-coach-agent-skill

Skill Claude CodeCodex needs its repo

The team-synergy-coach skill registry provides a comprehensive framework for registering, resolving, executing, and validating skills within the esports team training and coordination coaching harness. This document explains the complete skill lifecycle, from registration to execution and quality enforcement.

dungnotnull/used-cooking-oil-biodiesel-agent-skill

Skill Claude CodeCodex

Comprehensive documentation for skill registration, resolution, execution, validation, input/output JSON schemas, and tool definitions for the used-cooking-oil-biodiesel skill library.

tbvjvsladla/hermes-subagent-control-plane

Skill Claude CodeCodex

Use when an orchestrator must control a real Claude Code CLI sub-agent in another workspace. Reads the target agent-card.json, runs an auth/HOME preflight (no hardcoded paths), proves workspace context with a read-only discovery call, delegates bounded claude -p work with the correct workdir, and verifies results…

dungnotnull/standalone-solar-deep-station-agent-skill

Skill Claude CodeCodex

The standalone-solar-deep-station skill uses a modular, registry-based architecture that enables dynamic skill resolution, chain-of-thought routing, and graceful fallback. This document explains how skills are registered, resolved, executed, and validated.

dungnotnull/workshop-air-pollution-monitoring-agent-skill

Skill Claude CodeCodex

Production-grade skill registry & harness for Industrial Workshop Indoor Air Quality & Safety — registers, resolves, executes, and validates skills/tools/hooks with typed JSON-Schema contracts, a chain-of-thought router, lifecycle hooks, and a self-improving knowledge pipeline. Trigger whenever a user wants workshop…

LiuYihey/Agent-Engineering

Skill Claude CodeCodex

Production-hardened practices for building, debugging, and optimizing LLM agents with tools, streaming UI, and multi-turn sessions. Covers dual-store transcripts, artifact ownership, phase gating, orchestration tiers, failure classification, and root-cause fixes over patches. Use when designing agent loops, fixing…

dungnotnull/transmission-jitter-reduction-agent-skill

Skill Claude CodeCodex

The transmission-jitter-reduction skill is implemented as a modular skill-registry rather than a fixed pipeline. The markdown contract in skills/main.md describes the 6-step harness; the Python agent framework (tjr) makes that contract a dynamically-composable, schema-validated, hook-observable system. Each step is a…

dungnotnull/small-datacenter-airflow-thermal-optimization-agent-skill

Skill Claude CodeCodex

This document is the canonical reference for how skills are registered, resolved, executed, and validated in the dcthermal flexible agent & skill architecture for the small-datacenter-airflow-thermal-optimization domain.